{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:M5RZ3FE3E6SDHYCTD2FXXF6H5Y","short_pith_number":"pith:M5RZ3FE3","schema_version":"1.0","canonical_sha256":"67639d949b27a433e0531e8b7b97c7ee21f1336929d2a32db80ef860f63f1597","source":{"kind":"arxiv","id":"1710.05373","version":2},"attestation_state":"computed","paper":{"title":"Robust Locally-Linear Controllable Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Ghodsi, Ershad Banijamali, Hung Bui, Mohammad Ghavamzadeh, Rui Shu","submitted_at":"2017-10-15T18:22:44Z","abstract_excerpt":"Embed-to-control (E2C) is a model for solving high-dimensional optimal control problems by combining variational auto-encoders with locally-optimal controllers. However, the E2C model suffers from two major drawbacks: 1) its objective function does not correspond to the likelihood of the data sequence and 2) the variational encoder used for embedding typically has large variational approximation error, especially when there is noise in the system dynamics. In this paper, we present a new model for learning robust locally-linear controllable embedding (RCE). Our model directly estimates the pre"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1710.05373","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-15T18:22:44Z","cross_cats_sorted":[],"title_canon_sha256":"907a4b7a5669ab7febc0750b31b3b55bc5fa6161ee9f5018b7968ad923c91b7c","abstract_canon_sha256":"fa7b061cd1e738109461db5470eaf937d88bfd6c3af33dbeb952d86e3e51c52e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:49.215654Z","signature_b64":"AawYRxocy5FaucEVg8xIwyT1j/tE6cEvj8ixCXPt2LKqwuwlYLs8btiAvkqCSoxARgWbr2sRq8uLcBtirIHkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67639d949b27a433e0531e8b7b97c7ee21f1336929d2a32db80ef860f63f1597","last_reissued_at":"2026-05-18T00:22:49.215220Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:49.215220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Locally-Linear Controllable Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Ghodsi, Ershad Banijamali, Hung Bui, Mohammad Ghavamzadeh, Rui Shu","submitted_at":"2017-10-15T18:22:44Z","abstract_excerpt":"Embed-to-control (E2C) is a model for solving high-dimensional optimal control problems by combining variational auto-encoders with locally-optimal controllers. However, the E2C model suffers from two major drawbacks: 1) its objective function does not correspond to the likelihood of the data sequence and 2) the variational encoder used for embedding typically has large variational approximation error, especially when there is noise in the system dynamics. In this paper, we present a new model for learning robust locally-linear controllable embedding (RCE). Our model directly estimates the pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.05373","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1710.05373","created_at":"2026-05-18T00:22:49.215282+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.05373v2","created_at":"2026-05-18T00:22:49.215282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.05373","created_at":"2026-05-18T00:22:49.215282+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5RZ3FE3E6SD","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5RZ3FE3E6SDHYCT","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5RZ3FE3","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5RZ3FE3E6SDHYCTD2FXXF6H5Y","json":"https://pith.science/pith/M5RZ3FE3E6SDHYCTD2FXXF6H5Y.json","graph_json":"https://pith.science/api/pith-number/M5RZ3FE3E6SDHYCTD2FXXF6H5Y/graph.json","events_json":"https://pith.science/api/pith-number/M5RZ3FE3E6SDHYCTD2FXXF6H5Y/events.json","paper":"https://pith.science/paper/M5RZ3FE3"},"agent_actions":{"view_html":"https://pith.science/pith/M5RZ3FE3E6SDHYCTD2FXXF6H5Y","download_json":"https://pith.science/pith/M5RZ3FE3E6SDHYCTD2FXXF6H5Y.json","view_paper":"https://pith.science/paper/M5RZ3FE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.05373&json=true","fetch_graph":"https://pith.science/api/pith-number/M5RZ3FE3E6SDHYCTD2FXXF6H5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/M5RZ3FE3E6SDHYCTD2FXXF6H5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5RZ3FE3E6SDHYCTD2FXXF6H5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5RZ3FE3E6SDHYCTD2FXXF6H5Y/action/storage_attestation","attest_author":"https://pith.science/pith/M5RZ3FE3E6SDHYCTD2FXXF6H5Y/action/author_attestation","sign_citation":"https://pith.science/pith/M5RZ3FE3E6SDHYCTD2FXXF6H5Y/action/citation_signature","submit_replication":"https://pith.science/pith/M5RZ3FE3E6SDHYCTD2FXXF6H5Y/action/replication_record"}},"created_at":"2026-05-18T00:22:49.215282+00:00","updated_at":"2026-05-18T00:22:49.215282+00:00"}